Advertisement

Adapting Visual Category Models to New Domains

  • Kate Saenko
  • Brian Kulis
  • Mario Fritz
  • Trevor Darrell
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6314)

Abstract

Domain adaptation is an important emerging topic in computer vision. In this paper, we present one of the first studies of domain shift in the context of object recognition. We introduce a method that adapts object models acquired in a particular visual domain to new imaging conditions by learning a transformation that minimizes the effect of domain-induced changes in the feature distribution. The transformation is learned in a supervised manner and can be applied to categories for which there are no labeled examples in the new domain. While we focus our evaluation on object recognition tasks, the transform-based adaptation technique we develop is general and could be applied to non-image data. Another contribution is a new multi-domain object database, freely available for download. We experimentally demonstrate the ability of our method to improve recognition on categories with few or no target domain labels and moderate to large changes in the imaging conditions.

Keywords

Support Vector Machine Target Domain Domain Adaptation Source Domain Visual Domain 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Bay, H., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  2. 2.
    Blitzer, J., Dredze, M., Pereira, F.: Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In: ACL (2007)Google Scholar
  3. 3.
    Boiman, O., Shechtman, E., Irani, M.: In defense of nearest-neighbor based image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. IEEE, Los Alamitos (2008)Google Scholar
  4. 4.
    Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: CIVR (2007)Google Scholar
  5. 5.
    Chechik, G., Sharma, V., Shalit, U., Bengio, S.: Large scale online learning of image similarity through ranking. In: Pattern Recognition and Image Analysis (2009)Google Scholar
  6. 6.
    Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: Proc. CVPR (2005)Google Scholar
  7. 7.
    Daume III, H.: Frustratingly easy domain adaptation. In: ACL (2007)Google Scholar
  8. 8.
    Davis, J., Kulis, B., Jain, P., Sra, S., Dhillon, I.: Information-theoretic metric learning. In: ICML (2007)Google Scholar
  9. 9.
    Duan, L., Tsang, I.W., Xu, D., Maybank, S.J.: Domain transfer svm for video concept detection. In: CVPR (2009)Google Scholar
  10. 10.
    Fink, M.: Object classification from a single example utilizing class relevance metrics. In: Proc. NIPS (2004)Google Scholar
  11. 11.
    Hertz, T., Bar-Hillel, A., Weinshall, D.: Learning distance functions for image retrieval. In: CVPR (2004)Google Scholar
  12. 12.
    Hertz, T., Hillel, A.B., Weinshall, D.: Learning a kernel function for classification with small training samples. In: International Conference on Machine Learning (ICML), pp. 401–408 (2006)Google Scholar
  13. 13.
    Jiang, W., Zavesky, E., Chang, S., Loui, A.: Cross-domain learning methods for high-level visual concept classification. In: ICIP (2008)Google Scholar
  14. 14.
    Kulis, B., Jain, P., Grauman, K.: Fast similarity search for learned metrics. IEEE PAMI 39(12), 2143–2157 (2009)Google Scholar
  15. 15.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Visual domain adaptation using regularized cross-domain transforms. Technical Report UCB/EECS-2010-106, EECS Department, University of California, Berkeley (July 2010)Google Scholar
  16. 16.
    Stark, M., Goesele, M., Schiele, B.: A shape-based object class model for knowledge transfer. In: ICCV (2009)Google Scholar
  17. 17.
    Varma, M., Ray, D.: Learning the discriminative power-invariance trade-off. In: ICCV (2007)Google Scholar
  18. 18.
    Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: ACM Multimedia (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Kate Saenko
    • 1
  • Brian Kulis
    • 1
  • Mario Fritz
    • 1
  • Trevor Darrell
    • 1
  1. 1.UC Berkeley EECS and ICSIBerkeley

Personalised recommendations